mirror of
https://github.com/open-webui/open-webui.git
synced 2026-07-15 21:19:39 -05:00
[GH-ISSUE #8882] Feature request : Select text to send to image generation #118615
No Assignees
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: github-starred/open-webui#118615
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @chartrambiz on GitHub (Jan 24, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/8882
Hello!
Here is a neat feature I would like to see added in open-webui! No rush, please! I know the author is super busy! But the feature essentially is the ability to select text to send for image generation. The current image generation function sends the whole text the llm replied to the image generation configure in open-webui. I sometimes have to have the llm read back the message and ask it to not comment and then I can press the generate image button. I would like to be able to select a portion of the reply from the llm and have the generate image button there.
Also, my current setup is super modest. I run on low vram settings in comfy ui and Ollama will take up 4-5 gb of vram for the model depending on the model. When using ollama, it would be neat if we could offload the model from the vram to free it up for image generation models.
Thanks! I appreciate your work greatly! Looking forward to future updates!
@silentoplayz commented on GitHub (Jan 24, 2025):
Utilize the
Imagetoggle and you could avoid this problem entirely, as then, your prompt would be used for generating an image rather than the LLM's response output.This seems like a good feature request at first glance, but it might be difficult for the main developer or a contributor to come along and add as a feature.